Loading blueprint versions...
Please wait while we gather all the unique runs for this blueprint.
Please wait while we gather all the unique runs for this blueprint.
Please wait while we prepare the detailed comparison.
DTEF: Predict response distributions for Kazakhstan. Source: Global Dialogues GD1 (https://github.com/collect-intel/global-dialogues)
Average key point coverage extent for each model across all prompts.
| Prompts vs. Models | Claude 3.7 Sonnet | Claude 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 6th 80.5% | 21st 66.5% | 5th 81.0% | 2nd 83.0% | 4th 81.5% | 9th 77.0% | 7th 77.8% | 8th 77.3% | 15th 75.3% | 9th 77.0% | 18th 74.8% | 1st 83.3% | 9th 77.0% | 16th 74.8% | 20th 71.5% | 16th 74.8% | 14th 75.3% | 3rd 82.0% | 19th 72.0% | 12th 76.0% | 13th 75.5% | |
| 82.5% | 89% | 56% | 86% | 100% | 89% | 98% | 88% | 96% | 94% | 92% | 56% | 90% | 86% | 90% | 55% | 80% | 71% | 92% | 81% | 87% | 56% | |
| 73.2% | 77% | 70% | 83% | 82% | 76% | 72% | 76% | 70% | 67% | 70% | 77% | 82% | 70% | 71% | 73% | 76% | 70% | 77% | 66% | 76% | 56% | |
| 68.0% | 76% | 65% | 74% | 70% | 67% | 61% | 70% | 60% | 60% | 64% | 72% | 68% | 68% | 62% | 60% | 66% | 67% | 77% | 59% | 67% | 96% | |
| 83.6% | 80% | 75% | 81% | 80% | 94% | 77% | 77% | 83% | 80% | 82% | 94% | 93% | 84% | 76% | 98% | 77% | 93% | 82% | 82% | 74% | 94% |